2019

Improving Quality and Efficiency in Plan-based Neural Data-to-Text Generation

Moryossef, Amit, Dagan, Ido, Goldberg, Yoav

Understand

We follow the step-by-step approach to neural data-to-text generation we proposed in Moryossef et al (2019), in which the generation process is divided into a text-planning stage followed by a plan-realization stage.

  • We suggest four extensions to that framework: (1) we introduce a trainable neural planning component that can generate effective plans several orders of magnitude faster than the original planner; (2) we incorporate typing hints that improve the model's ability to deal with unseen relations and entities; (3) we introduce a verification-by-reranking stage that substantially improves the faithfulness of the resulting texts; (4) we incorporate a simple but effective referring expression generation module.
  • These extensions result in a generation process that is faster, more fluent, and more accurate.

Built on

Similar

  • Individual and domain adaptation in sentence planning for dialogue

    Marilyn A Walker, Amanda Stent, François Mairesse, and Rashmi Prasad. 2007 · 2007

    Cited alongside, same era.

  • Integrating graph-based and transition-based dependency parsers

    Joakim Nivre and Ryan McDonald. 2008 · 2008

    Cited alongside, same era.

  • The webnlg challenge: Generating text from dbpedia data

    Emilie Colin, Claire Gardent, Yassine Mrabet, Shashi Narayan, and Laura Perez-Beltrachini. 2016 · 2016

    Cited alongside, same era.

  • Globally coherent text generation with neural checklist models

    Chloé Kiddon, Luke Zettlemoyer, and Yejin Choi. 2016 · 2016

    Cited alongside, same era.

  • Survey of the state of the art in natural language generation: Core tasks, applications and evaluation

    Original

    Albert Gatt and Emiel Krahmer. 2017 · 2017

    Cited alongside, same era.

Then

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…